PhD student Hyunjae Kim, from the System Health and Risk Management Lab (Advisor: Prof. Byeng Dong Youn) of Seoul National University Dept. of Mechanical and Aerospace Engineering, received Best Poster Award at 2019 PHM Korea Conference for his paper titled “Data Augmentation Using Cepstrum Editing for Deep Learning-based Fault.”

<?xml:namespace prefix = "o" ns = "urn:schemas-microsoft-com:office:office" />

In the above paper, Mr. Kim used the Ceptrum Editing technique to increase the fault vibration signal. By using this in deep learning, he was able to increase the accuracy of fault detection. The suggested method can increase the amount of fault data, which is difficult to acquire in industrial sites, and contribute to the development of a deep learning-based fault diagnosis model.